SetFit with mini1013/master_domain

This is a SetFit model that can be used for Text Classification. This SetFit model uses mini1013/master_domain as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

  1. Fine-tuning a Sentence Transformer with contrastive learning.
  2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

Model Sources

Model Labels

Label Examples
7
  • '와콤 CTL-472 웹툰 입문용 타블렛 펜 온라인강의 주식회사 지디스엠알오'
  • '와콤 타블렛 CTL-4100 와콤인튜어스 웹툰 (주)코티니'
  • '와콤 신티크16 DTK-1660 케이에이씨앤씨'
1
  • '브라더공식판매대리점 DCP-T426W 무한잉크복합기 인쇄 복사 스캔 무선 AS연장 (주)대명아이티'
  • '교세라 ECOSYS M5521cdn 컬러레이저복합기 정품토너포함 한라테크'
  • 'DCP-T720DW 브라더정품 무한잉크복합기 인쇄 복사 스캔 자동양면인쇄 (주)진전산시스템'
4
  • '로지텍 코리아 미니멀 무선 일루미네이티드 키보드 MX KEYS MINI 블랙(그라파이트) 주식회사 자강정보통신'
  • '앱코 K660 축교환 완전방수 게이밍 카일광축 레인보우LED 블랙,리니어 에스티에스컴퍼니'
  • 'ABKO HACKER K523 기계식 축교환 LED 키패드 주식회사 브라보세컨즈'
2
  • '브라더 TN-2380 정품토너 2.6K HL L2365DW HL L2360dn MFC L2700D MFC L2700DW 주식회사 휴먼아이티'
  • '삼성전자정품 폐토너통 CLT-W406/ C510W/ C513W/ C563W/ C563FW 엘케이솔루션'
  • '(HP) No.680 정품 F6V27AA 검정 정품잉크 검정 총1개만구매(2개이상주문시발송안됨) 밀알시스템'
6
  • '와콤원 펜 CP91300B2Z 삼성갤럭시탭,갤럭시노트,오닉스 호환 펜 '
  • '드로잉장갑 와콤 신티크 XP-PEN 휴이온 액정타블렛 아이패드 태블릿 터치오류방지 '
  • '드로잉장갑 와콤 신티크 XP-PEN 휴이온 액정타블렛 아이패드 태블릿 터치오류방지 '
8
  • '◆◆ 정품 샘플테이프 + ◆◆ 브라더 正品 이름 라벨스티커기계 PT-P900W QR코드 wifi ◀正品▶ PT-P900W 탑정보기술'
  • '가제트 3D펜 GP3000+5M PLA 필라멘트 세트(24색) (주)위드피플즈'
  • '인스탁스 와이드 링크 포토프린터 모카 그레이(+아크릴액자) 한국후지필름 (주)'
3
  • '엡손 DS-30000, 양면 스캐너 A3 주식회사 케이에스샵'
  • '엡손 WorkForce DS-50000 (주)테드이십일'
  • '엡손스캐너 ES-580WMLP 미니멀 라이프 패키지(ES-580W+재단기+롤러)북스캐너 (주)에이엔에이코리아'
5
  • '로지텍 MK295 SILENT WIRELESS COMBO (화이트) (주)아토닉스'
  • '로지텍 MK275 영문자판 병행수입 제이제이 인터내셔널'
  • '로지텍코리아 시그니처 MK650 무선 합본 (그래파이트) 주식회사 지엠샤이'
0
  • 'ROCCAT KONE PRO AIR (블랙) (주)디아씨앤씨'
  • '[Logitech]로지텍 Trackman Marble USB 마우스 트랙맨 트랙볼 마블 마우스 벌크 /택배/병행/ 당일출고 Trackman Marble USB 허브포스트'
  • '로지텍 G402 Hyperion Fury (주)케이엘시스템'

Evaluation

Metrics

Label Metric
all 0.8548

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("mini1013/master_cate_el18")
# Run inference
preds = model("Pulsar X2V2 미니 무선 게이밍 마우스 (블랙)  와이에스비투비")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 4 10.5569 27
Label Training Sample Count
0 50
1 50
2 50
3 50
4 50
5 50
6 13
7 50
8 50

Training Hyperparameters

  • batch_size: (512, 512)
  • num_epochs: (20, 20)
  • max_steps: -1
  • sampling_strategy: oversampling
  • num_iterations: 40
  • body_learning_rate: (2e-05, 2e-05)
  • head_learning_rate: 2e-05
  • loss: CosineSimilarityLoss
  • distance_metric: cosine_distance
  • margin: 0.25
  • end_to_end: False
  • use_amp: False
  • warmup_proportion: 0.1
  • seed: 42
  • eval_max_steps: -1
  • load_best_model_at_end: False

Training Results

Epoch Step Training Loss Validation Loss
0.0154 1 0.4961 -
0.7692 50 0.1923 -
1.5385 100 0.0615 -
2.3077 150 0.0532 -
3.0769 200 0.0513 -
3.8462 250 0.0283 -
4.6154 300 0.0313 -
5.3846 350 0.0258 -
6.1538 400 0.0174 -
6.9231 450 0.0053 -
7.6923 500 0.0021 -
8.4615 550 0.0039 -
9.2308 600 0.0059 -
10.0 650 0.0001 -
10.7692 700 0.0001 -
11.5385 750 0.0001 -
12.3077 800 0.0001 -
13.0769 850 0.0001 -
13.8462 900 0.0 -
14.6154 950 0.0001 -
15.3846 1000 0.0 -
16.1538 1050 0.0 -
16.9231 1100 0.0 -
17.6923 1150 0.0 -
18.4615 1200 0.0 -
19.2308 1250 0.0 -
20.0 1300 0.0 -

Framework Versions

  • Python: 3.10.12
  • SetFit: 1.1.0.dev0
  • Sentence Transformers: 3.1.1
  • Transformers: 4.46.1
  • PyTorch: 2.4.0+cu121
  • Datasets: 2.20.0
  • Tokenizers: 0.20.0

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}
Downloads last month
702
Safetensors
Model size
111M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mini1013/master_cate_el18

Base model

klue/roberta-base
Finetuned
(132)
this model

Evaluation results